Skip to content

Instantly share code, notes, and snippets.

@Qian-Li
Qian-Li / agent-coordination-retro.md
Created May 21, 2026 17:26
Coordinating coding agents across a multi-issue sprint: what we saw — retro from a real run

Coordinating coding agents across a multi-issue sprint: what we saw

A short retrospective from a sprint where one coordinator agent supervised individual coding agents working on consecutive, dependency-linked issues. Generalized from a real run; concrete examples linked at the bottom.

Setup

Two LLM agent layers running against the same repo:

  • Coordinator agent — owns sprint-level state. Reviews plans, reviews completion reports, files follow-up issues, edits the canonical sprint doc.
  • Coding agents — one per issue. Read the issue body, sprint plan, ADRs, governing instructions (e.g. a repo-level CLAUDE.md), and prior PR diffs. Propose a plan with acceptance criteria. Implement in an isolated branch/worktree. Produce a completion report aligned with the AC set.